Upload 2 files

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

test.py

@@ -0,0 +1,58 @@
+import optuna
+import yaml
+import joblib
+import os
+import pandas as pd
+import matplotlib.pyplot as plt
+
+from sklearn.datasets import load_iris
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+from optuna.visualization.matplotlib import plot_optimization_history, plot_param_importances
+
+os.makedirs("models", exist_ok=True)
+os.makedirs("plots", exist_ok=True)
+
+def objective(trial):
+    n_estimators = trial.suggest_int("n_estimators", 50, 300)
+    max_depth = trial.suggest_int("max_depth", 2, 32)
+
+    data = load_iris()
+    X_train, X_test, y_train, y_test = train_test_split(data.data, data.target)
+
+    clf = RandomForestClassifier(n_estimators=n_estimators, max_depth=max_depth)
+    clf.fit(X_train, y_train)
+
+    accuracy = accuracy_score(y_test, clf.predict(X_test))
+    return accuracy
+
+study = optuna.create_study(direction="maximize")
+study.optimize(objective, n_trials=30)
+
+# Save trial results
+study_df = study.trials_dataframe()
+study_df.to_csv("models/study_trials.csv", index=False)
+
+# Save best parameters
+with open("models/best_params.yaml", "w") as f:
+    yaml.dump(study.best_trial.params, f)
+
+# Train final model with best parameters
+best_params = study.best_trial.params
+final_model = RandomForestClassifier(**best_params)
+data = load_iris()
+X_train, X_test, y_train, y_test = train_test_split(data.data, data.target)
+final_model.fit(X_train, y_train)
+
+# Save model
+joblib.dump(final_model, "models/best_model.pkl")
+
+# Save Optuna plots
+plot_optimization_history(study)
+plt.savefig("plots/optimization_history.png")
+plt.clf()
+
+plot_param_importances(study)
+plt.savefig("plots/param_importances.png")
+